The Data-Driven δ-Generalized Labeled Multi-Bernoulli Tracker for Automatic Birth Initialization
The δ-generalized labeled multi-Bernoulli (δ-GLMB) tracker is the first multiple hypothesis tracking (MHT)-like tracker that is provably Bayes-optimal. However, in its basic form, the δ-GLMB provides no mechanism for adaptively initializing targets at their first appearance from unlabeled measurements. By introducing a new multitarget likelihood function that accounts for new target appearance, a data-driven δ-GLMB tracker is derived that automatically initializes new targets in the tracker measurement update. Monte Carlo results of simulated multitarget tracking problems demonstrate improved multitarget tracking accuracy over comparable adaptive birth methods.
K. A. Legrand and K. J. Demars, "The Data-Driven δ-Generalized Labeled Multi-Bernoulli Tracker for Automatic Birth Initialization," Proceedings of SPIE - The International Society for Optical Engineering, vol. 10646, SPIE, Apr 2018.
The definitive version is available at https://doi.org/10.1117/12.2304664
Signal Processing, Sensor/Information Fusion, and Target Recognition XXVII 2018 (2018: Apr. 16-19, Orlando, FL)
Mechanical and Aerospace Engineering
Keywords and Phrases
Monte Carlo methods, Bayes-optimal; Likelihood functions; Measurement updates; Monte Carlo results; Multi-Bernoulli; Multi-target tracking; Multiple hypothesis tracking; Multitarget, Signal processing
International Standard Book Number (ISBN)
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2018 SPIE, All rights reserved.